Calibration
Terminal-Bench 2.0 → Terminal-Bench 2.1 (Vals AI)
Terminal-Bench 2.1 (Vals AI) is estimated from Terminal-Bench 2.0 with a linear curve fitted on 18 models measured on both: y = 0.8891·x + -0.0075, R² = 0.75, cross-validated error 6.3 pp. It is used for 17 estimates.
| Estimated model | Terminal-Bench 2.0 | Terminal-Bench 2.1 (Vals AI) | Source |
|---|---|---|---|
| GPT-5.3 Codex | 77.3% | 68.0% | estimated ± 6.3 pp, medium confidence |
| Composer 2 | 61.7% | 54.1% | estimated ± 6.3 pp, medium confidence |
| Claude Opus 4.5 | 59.3% | 52.0% | estimated ± 6.3 pp, medium confidence |
| Qwen3.6-27B | 59.3% | 52.0% | estimated ± 6.3 pp, medium confidence |
| Hy3 Preview | 54.4% | 47.6% | estimated ± 6.3 pp, medium confidence |
| Qwen3.5 397B | 52.5% | 45.9% | estimated ± 6.3 pp, medium confidence |
| Qwen3.6-35B-A3B | 51.5% | 45.0% | estimated ± 6.3 pp, medium confidence |
| Kimi K2.5 | 50.8% | 44.4% | estimated ± 6.3 pp, medium confidence |
| Kimi K2.5 (Reasoning) | 50.8% | 44.4% | estimated ± 6.3 pp, medium confidence |
| Claude Sonnet 4.5 | 50.0% | 43.7% | estimated ± 6.3 pp, medium confidence |
| Qwen3.5-122B-A10B | 49.4% | 43.2% | estimated ± 6.3 pp, medium confidence |
| MAI-Thinking-1 | 46.0% | 40.2% | estimated ± 6.3 pp, medium confidence |
| Qwen3.5-27B | 41.6% | 36.2% | estimated ± 6.3 pp, medium confidence |
| GLM-4.7 | 41.0% | 35.7% | estimated ± 6.3 pp, medium confidence |
| Qwen3.5-35B-A3B | 40.5% | 35.3% | estimated ± 6.3 pp, medium confidence |
| Laguna XS 2.1 | 37.5% | 32.6% | estimated ± 6.3 pp, medium confidence |
| LongCat-Flash-Lite-Sparse | 33.7% | 29.2% | estimated ± 6.3 pp, low confidence |
Fitted on
| Model | Terminal-Bench 2.0 | Terminal-Bench 2.1 (Vals AI) |
|---|---|---|
| Claude Sonnet 4.6 | 59.1% | 57.3% |
| Composer 2.5 | 69.3% | 58.4% |
| DeepSeek V4 Flash 0731 | 56.9% | 67.0% |
| DeepSeek V4 Pro 0813 | 67.9% | 54.7% |
| GLM-5.1 | 63.5% | 56.9% |
| GPT-5.4 mini | 60.0% | 54.7% |
| GPT-5.4 nano | 46.3% | 41.6% |
| GPT-5.5 | 82.0% | 76.4% |
| Grok 4.20 | 47.1% | 44.2% |
| Kimi K2.6 | 66.7% | 53.6% |
| Laguna M.1 | 45.8% | 34.1% |
| Laguna XS.2 | 35.7% | 25.8% |
| MiMo-V2.5 | 65.8% | 60.7% |
| MiMo-V2.5-Pro | 68.4% | 57.3% |
| MiniMax M2.7 | 57.0% | 48.7% |
| Qwen3.6 Plus | 61.6% | 53.2% |
| Qwen3.7 Max | 69.7% | 61.0% |
| Qwen3.7 Plus | 70.3% | 52.8% |